Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1244561 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1378. Min Act: -0.0000

Data Index: 464968 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1880341 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1748296 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1142518 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1682583 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8953. Min Act: -0.0000

Data Index: 544117 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1453731 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.7965. Min Act: -0.0000

Data Index: 646369 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.7167. Min Act: -0.0000

Data Index: 728635 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1476322 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6918. Min Act: -0.0000

Data Index: 25676 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1635887 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1414861 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6323. Min Act: -0.0000

Data Index: 15811 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1416219 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6944. Min Act: -0.0000

Data Index: 609940 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6493. Min Act: -0.0000

Data Index: 920734 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1169530 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.6259. Min Act: 0.0000

Data Index: 588458 (The Pile)

Max Activating Token Index: 298